
# Computations
import numpy as np
import pandas as pd

from datetime import datetime, timedelta
from collections import Counter

# Visualisation libraries

## progressbar
import progressbar

## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output

## plotly
from plotly.offline import init_notebook_mode, iplot 
import plotly.figure_factory as ff
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px

## seaborn
import seaborn as sns

##
import missingno as msno

## matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, Polygon
from matplotlib.font_manager import FontProperties
import matplotlib.colors as mcolors
from matplotlib import cm
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
plt.style.use('seaborn-whitegrid')
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
plt.rcParams['text.color'] = 'k'
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")


Data = pd.read_csv("Data/netflix_titles.csv")
Data.head(5)


def Data_info(Inp, Only_NaN = False):
    Out = Inp.dtypes.to_frame(name='Data Type').sort_values(by=['Data Type'])
    Out = Out.join(Inp.isnull().sum().to_frame(name = 'Number of NaN Values'), how='outer')
    Out ['Size'] = Inp.shape[0]
    Out['Percentage'] = 100 - np.round(100*(Out['Number of NaN Values']/Inp.shape[0]),2)
    Out.index.name = 'Features'
    Out['Data Type'] = Out['Data Type'].astype(str)
    if Only_NaN:
        Out = Out.loc[Out['Number of NaN Values']>0]
    return Out

data_info = Data_info(Data).reset_index(drop = False)
fig = px.bar(data_info, x= 'Features', y= 'Percentage', color = 'Data Type', text = 'Data Type',
            color_discrete_sequence = ['PaleGreen', 'LightBlue', 'PeachPuff'], hover_data = data_info.columns)
fig.update_layout(plot_bgcolor= 'white', legend=dict(x=1, y=.5, traceorder="normal",
                                                     bordercolor="DarkGray", borderwidth=1), width = 700)
fig.update_traces(texttemplate= 6*' ' + '%{label}', textposition='inside')
fig.update_traces(marker_line_color= 'Black', marker_line_width=1., opacity=1)
fig.show()


_ = msno.dendrogram(Data, figsize=(16,6), fontsize=14)


Data['date_added'] = pd.to_datetime(Data['date_added'].fillna('January 01, 2020'))


Data['year_added'] = Data['date_added'].apply(lambda x: x.year).astype(int)
Data['month_added'] = Data['date_added'].apply(lambda x: x.month).astype(int)
Data['month_name'] = Data['date_added'].apply(lambda x: x.month_name())


Temp0 = Data.loc[Data.year_added< 2020].groupby(['year_added'])['year_added'].agg({'count'})
Temp0.sort_values(inplace = True, by=['year_added'])
Temp0.reset_index(inplace = True, drop= False)
Temp1 = Data.loc[Data.year_added< 2020].groupby(['type','year_added'])['year_added'].agg({'count'})
Temp1.sort_values(inplace = True, by=['year_added'])
Temp1.reset_index(inplace = True, drop= False)

Group = Temp1.merge(Temp0, left_on='year_added', right_on='year_added')
Group.rename(columns = {'count_x': 'count', 'count_y': 'total'},inplace = True)
Group['Percentage'] = 100*(Group['count']/Group['total'])
Group = Group.round(2)
del Temp0, Temp1
display(Group)


fig, ax = plt.subplots(2, 1, figsize=(14, 12))
_ = Group.loc[Group.type == 'Movie'].plot(ax =ax[0], x= 'year_added',
                                                     y = 'total', color= '#34495e', linewidth=2, label='Total')
_ = Group.loc[Group.type == 'Movie'].plot(ax= ax[0], x= 'year_added',
                                                     y = 'count', color='#e74c3c', linewidth=2, label='Movies')
_ = Group.loc[Group.type == 'TV Show'].plot(ax= ax[0], x= 'year_added',
                                                       y = 'count', color='#9b59b6', linewidth=2, label='TV Shows')
_ = ax[0].set_ylim([0,2500])
_ = ax[0].set_xlim([Group.year_added.min(), Group.year_added.max()])
_ = ax[0].set_xticks(np.arange(Group.year_added.min(), Group.year_added.max()+1, 1))
_ = ax[0].set_xlabel('Year Added')
_ = ax[0].set_ylabel('Count')
_ = ax[0].legend(bbox_to_anchor=(1, 1), fontsize = 14)


_ = sns.barplot(ax = ax[1], x="year_added", y="Percentage", hue = 'type', palette='Purples',
                edgecolor='k',  hatch="///", data=Group)
_ = ax[1].legend(bbox_to_anchor=(1, 1), fontsize = 14)
_ = ax[1].set_ylim([0,100])
_ = ax[1].set_yticks(np.arange(0, 101, 10))
_ = ax[1].set_xlabel('Year Added')
_ = ax[1].set_ylabel('Percentage')


Group = Data.loc[Data.year_added<2020].groupby(['year_added',
                                                'month_added'])['year_added'].agg({'count'}).unstack().fillna(0).T

Temp = Data[['month_added','month_name']].sort_values(by=['month_added'])
Temp = Temp.month_name.unique().tolist()

fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(10, 8))
cs = ax.pcolor(Group, cmap='BuGn', edgecolors='white', linewidths=2)
_ = ax.set_xticks(np.arange(0.5, len(Group.columns), 1))
_ = ax.set_xticklabels(Group.columns, fontsize = 14)
_ = ax.set_yticks(np.arange(0.5, len(Group.index), 1))
_ = ax.set_yticklabels(Temp, fontsize = 14)
_ = ax.set_title('Contents Added/Updated by Months', fontsize=14)
_ = fig.colorbar(cs, ax=ax, shrink=1)


def Col_Sep(Col, df = Data):
    Out = pd.Series(dict(Counter(", ".join(df[Col].dropna()).split(", "))))
    Out = Out.sort_values(ascending = False)
    Out = pd.DataFrame(Out).reset_index(drop = False)
    return Out

Group = Col_Sep('country')
Group.columns = ['Country','Count']

fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(13, 6))

_ = sns.barplot(ax = ax[0], y="Country", x="Count", palette='summer',
                edgecolor='k',  hatch="///", data = Group[:10])
_ = ax[0].set_xlim([0, 3e3])

Top = 10
E = [0 for _ in range(Top)]
E[0] = 0.05
_ = Group[:Top].plot.pie(ax = ax[1],y= 'Count', startangle=90, label = '', labels = None,
                         colors = sns.color_palette("Paired"), legend=True, autopct='%1.1f%%', fontsize=10,
                         pctdistance=0.85, explode = E)

_ = ax[1].legend(bbox_to_anchor=(1, 1), labels= Group[:Top].Country)
_ = ax[1].add_artist(plt.Circle((0,0),0.70,fc='white'))
_ = ax[1].set_xlabel('Top %i Content Producers' % Top, fontsize = 14)


Group = Data.dropna().groupby(['type','rating'])['rating'].agg({'count'})
Group.reset_index(drop = False, inplace = True)
print('Movie Ratings:')
Group['rating group'] = np.nan
Group.loc[Group.rating.isin(['G', 'TV-Y', 'TV-G']), 'rating group'] = 'Little Kids'
Group.loc[Group.rating.isin(['PG', 'TV-Y7', 'TV-Y7-FV', 'TV-PG']), 'rating group'] = 'Older Kids'
Group.loc[Group.rating.isin(['PG-13', 'TV-14']), 'rating group'] = 'Teens'
Group.loc[Group.rating.isin(['R', 'NC-17', 'TV-MA']), 'rating group'] = 'Mature'
Group.loc[Group.rating.isin(['NR', 'UR']), 'rating group'] = 'Unrated'
Group.sort_values(by=['rating group'], inplace = True)
display(Group.style.hide_index())

Movie Ratings:


RG = Group.loc[(Group.type == 'Movie'), 'rating group'].unique()

fig, ax = plt.subplots(nrows=1, ncols=len(RG), figsize=(13, 6), sharey = True)
C =  ['forestgreen','mediumseagreen','bisque','coral','gray']

for i in range(len(RG)):
    Temp = Group.loc[(Group.type == 'Movie') & (Group['rating group'] == RG[i])]
    _ = sns.barplot(ax=ax[i], x='rating', y ='count', data=Temp, linewidth=2.5,
                    facecolor=C[i], errcolor=".3", edgecolor=".3", hatch = '//')
    _ = ax[i].set_xlabel(None)
    _ = ax[i].set_ylabel(None)
    _ = ax[i].set_xticklabels(ax[i].get_xticklabels(), rotation=90)
    
_ = ax[0].set_ylim([0,1400])  
_ = ax[0].set_ylabel('Count')
st = fig.suptitle("Netflix Maturity Rating (Movies)", fontsize="x-large")
st.set_y(0)

del RG, C, Temp
fig.tight_layout()


Group.loc[(Group.type == 'TV Show')]


RG = Group.loc[(Group.type == 'TV Show'), 'rating group'].unique()

fig, ax = plt.subplots(nrows=1, ncols=len(RG), figsize=(10, 6), sharey = True)
C =  ['forestgreen','mediumseagreen','bisque','coral','gray']

for i in range(len(RG)):
    Temp = Group.loc[(Group.type == 'TV Show') & (Group['rating group'] == RG[i])]
    _ = sns.barplot(ax=ax[i], x='rating', y ='count', data=Temp, linewidth=2.5,
                    facecolor=C[i], errcolor=".3", edgecolor=".3", hatch = '//')
    _ = ax[i].set_xlabel(None)
    _ = ax[i].set_ylabel(None)
    _ = ax[i].set_xticklabels(ax[i].get_xticklabels(), rotation=90)
    
_ = ax[0].set_ylim([0,50])  
_ = ax[0].set_ylabel('Count')
st = fig.suptitle("Netflix Maturity Rating (TV Shows)", fontsize="x-large")
st.set_y(0)

del RG, C, Temp
fig.tight_layout()


fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(16, 6), sharey = True)

Temp = Group.groupby(['rating group'])['count'].agg({'sum'})

E = [0.06 for _ in range(len(Temp))]
# E[0] = 0.05
_ = Temp.plot.pie(ax = ax,y= 'sum', startangle=90, label = '', labels = None,
                         colors = sns.color_palette("Paired"), legend=True, autopct='%1.1f%%', fontsize=12,
                         pctdistance=0.85, explode = E, wedgeprops={"linewidth": 1.5, "edgecolor": 'gray'})
_ = ax.legend(bbox_to_anchor=(2, 0.7), loc="center left", labels= Temp.index, fontsize = 14)
_ = ax.add_artist(plt.Circle((0,0),0.70,fc='white'))
_ = ax.set_title('Netflix Rating Groups')


Group = Col_Sep('listed_in')
Group.columns = ['Category','Count']


fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(16, 6), sharey = True)
_ = sns.barplot(ax = ax, x="Category", y="Count", palette='RdPu', edgecolor='k',  hatch="///", data=Group)
_ = ax.set_xticklabels(ax.get_xticklabels(), rotation=90, fontsize = 12)
_ = ax.set_ylim([0,2e3])


Top = 10
Group = Col_Sep('country', Data.loc[Data.type == 'Movie'])
Group.columns = ['Country','Count']
Temp = Group[:5]['Country'].tolist()
del Group
i = Temp[0]
Temp0 =Data.loc[(Data['country'].str.contains(i, regex=False) ==True) & (Data.type == 'Movie')]
Temp0 = Col_Sep('cast', df = Temp0)[:Top]
Temp0['Country'] = i
Group = Temp0.copy()
for i in Temp[1:]:
    Temp0 =Data.loc[(Data['country'].str.contains(i, regex=False) ==True) & (Data.type == 'Movie')]
    Temp0 = Col_Sep('cast', df = Temp0)[:Top]
    Temp0['Country'] = i
    Group = pd.concat([Group, Temp0])
    del Temp0
    
Group.columns = ['Actor', 'Count', 'Country']


fig, ax = plt.subplots(nrows=1, ncols=len(Temp), figsize=(16, 6), sharey = True)
C =  ['Blues','OrRd','winter','spring','summer']

for i in range(len(Temp)):
    Temp0 = Group.loc[(Group['Country'] == Temp[i])]
    _ = sns.barplot(ax=ax[i], x='Actor', y ='Count', data=Temp0, palette= C[i], edgecolor='k',  hatch="///")
    _ = ax[i].set_xlabel(Temp[i])
    _ = ax[i].set_ylabel(None)
    _ = ax[i].set_xticklabels(ax[i].get_xticklabels(), rotation=90)
del Temp, Temp0

_ = ax[0].set_ylim([0,35])  
_ = ax[0].set_ylabel('Count')
st = fig.suptitle("Most appeared movie actors in Netflix library by country", fontsize="x-large")
st.set_y(1)


Top = 10
Group = Col_Sep('country', Data.loc[Data.type == 'TV Show'])
Group.columns = ['Country','Count']
Temp = Group[:5]['Country'].tolist()
del Group
i = Temp[0]
Temp0 =Data.loc[(Data['country'].str.contains(i, regex=False) ==True) & (Data.type == 'TV Show')]
Temp0 = Col_Sep('cast', df = Temp0)[:Top]
Temp0['Country'] = i
Group = Temp0.copy()
for i in Temp[1:]:
    Temp0 =Data.loc[(Data['country'].str.contains(i, regex=False) ==True) & (Data.type == 'TV Show')]
    Temp0 = Col_Sep('cast', df = Temp0)[:Top]
    Temp0['Country'] = i
    Group = pd.concat([Group, Temp0])
    del Temp0
    
Group.columns = ['Actor', 'Count', 'Country']


fig, ax = plt.subplots(nrows=1, ncols=len(Temp), figsize=(16, 6), sharey = True)
C =  ['Blues','OrRd','winter','spring','summer']

for i in range(len(Temp)):
    Temp0 = Group.loc[(Group['Country'] == Temp[i])]
    _ = sns.barplot(ax=ax[i], x='Actor', y ='Count', data=Temp0, palette= C[i], edgecolor='k',  hatch="///")
    _ = ax[i].set_xlabel(Temp[i])
    _ = ax[i].set_ylabel(None)
    _ = ax[i].set_xticklabels(ax[i].get_xticklabels(), rotation=90)
del Temp, Temp0

_ = ax[0].set_ylim([0,18])  
_ = ax[0].set_ylabel('Count')
st = fig.suptitle("Most appeared TV show actors in Netflix library by country", fontsize="x-large")
st.set_y(1)

	show_id	type	title	director	cast	country	date_added	release_year	rating	duration	listed_in	description
0	81145628	Movie	Norm of the North: King Sized Adventure	Richard Finn, Tim Maltby	Alan Marriott, Andrew Toth, Brian Dobson, Cole...	United States, India, South Korea, China	September 9, 2019	2019	TV-PG	90 min	Children & Family Movies, Comedies	Before planning an awesome wedding for his gra...
1	80117401	Movie	Jandino: Whatever it Takes	NaN	Jandino Asporaat	United Kingdom	September 9, 2016	2016	TV-MA	94 min	Stand-Up Comedy	Jandino Asporaat riffs on the challenges of ra...
2	70234439	TV Show	Transformers Prime	NaN	Peter Cullen, Sumalee Montano, Frank Welker, J...	United States	September 8, 2018	2013	TV-Y7-FV	1 Season	Kids' TV	With the help of three human allies, the Autob...
3	80058654	TV Show	Transformers: Robots in Disguise	NaN	Will Friedle, Darren Criss, Constance Zimmer, ...	United States	September 8, 2018	2016	TV-Y7	1 Season	Kids' TV	When a prison ship crash unleashes hundreds of...
4	80125979	Movie	#realityhigh	Fernando Lebrija	Nesta Cooper, Kate Walsh, John Michael Higgins...	United States	September 8, 2017	2017	TV-14	99 min	Comedies	When nerdy high schooler Dani finally attracts...

	type	year_added	count	total	Percentage
0	Movie	2008	1	2	50.00
1	TV Show	2008	1	2	50.00
2	Movie	2009	2	2	100.00
3	Movie	2010	1	1	100.00
4	Movie	2011	13	13	100.00
5	Movie	2012	4	7	57.14
6	TV Show	2012	3	7	42.86
7	Movie	2013	6	12	50.00
8	TV Show	2013	6	12	50.00
9	Movie	2014	19	25	76.00
10	TV Show	2014	6	25	24.00
11	TV Show	2015	32	90	35.56
12	Movie	2015	58	90	64.44
13	TV Show	2016	192	456	42.11
14	Movie	2016	264	456	57.89
15	TV Show	2017	387	1300	29.77
16	Movie	2017	913	1300	70.23
17	Movie	2018	1290	1782	72.39
18	TV Show	2018	492	1782	27.61
19	Movie	2019	1546	2349	65.82
20	TV Show	2019	803	2349	34.18

Data Description¶

Inspiration¶

Loading the Data¶

Exploratory Data Analysis¶

Year Added¶

Country¶

Rating¶

Categories¶

References¶

Rating	Meaning
G	General Audiences
PG	Parental Guidance Suggested
PG-13	Parents Stongly Cautioned
R	Restricted
NC-17	Adults Only
Unrated	Unrated

type	rating	count	rating group
Movie	G	35	Little Kids
TV Show	TV-G	1	Little Kids
TV Show	TV-Y	3	Little Kids
Movie	TV-G	53	Little Kids
Movie	TV-Y	21	Little Kids
Movie	R	500	Mature
Movie	TV-MA	1157	Mature
TV Show	R	1	Mature
Movie	NC-17	1	Mature
TV Show	TV-MA	32	Mature
Movie	PG	176	Older Kids
Movie	TV-PG	344	Older Kids
Movie	TV-Y7	42	Older Kids
Movie	TV-Y7-FV	11	Older Kids
TV Show	TV-PG	14	Older Kids
TV Show	TV-Y7	6	Older Kids
Movie	TV-14	878	Teens
TV Show	TV-14	39	Teens
Movie	PG-13	278	Teens
Movie	NR	175	Unrated
Movie	UR	7	Unrated